View in EDS

Enhanced Cross-Modal Hashing via Hybrid Distillation and Structural Refinement.

Saved in:
Bibliographic Details
Title: Enhanced Cross-Modal Hashing via Hybrid Distillation and Structural Refinement.
Authors: Liu, Xiaoqing1 ft_liuxiaoqing@mail.scut.edu.cn, Yu, Zhiwen2 zhwyu@scut.edu.cn, Yang, Kaixiang2 yangkx@scut.edu.cn, Yu, Jun3 yujun@hit.edu.cn, Zeng, Huanqiang4 zeng0043@hqu.edu.cn, Philip Chen, C. L.2 Philip.Chen@ieee.org
Source: IEEE Transactions on Image Processing. 2025, Vol. 34, p7138-7151. 14p.
Subjects: Machine learning, Hashing, Machine theory, Message authentication codes, Electronic file management
Abstract: Since cross-modal hashing requires minimal storage and computation, it is becoming increasingly popular with the exponential growth of multimedia content on the internet. However, the lack of accurate supervisory data has curtailed the effectiveness of unsupervised hashing techniques. Conversely, supervised hashing strategies necessitate considerable human and financial resources for data annotation. To address this limitation, we propose a novel semi-supervised cross-modal hashing method called Enhanced Cross-Modal Hashing via Hybrid Distillation and Structural Refinement (HDSR). Specifically, we first learn the features of inter-modal and inter-instance similarity relationships through pointwise semantic alignment and listwise similarity partial order learning, respectively, to extract refined structural representations from partially labeled data. Secondly, by fusing inter-modal similarity to construct higher-order affinity matrices, we precisely delineate the semantic correlation information across cross-modal data, facilitating stable self-supervised training of unlabeled data through the application of momentum fusion strategies. Finally, the refined structural representation of labeled data is transferred into unlabeled branches through hybrid distillation, enhancing the performance of cross-modal hash learning by generating compact and accurate hash codes. The proposed HDSR is compared with several state-of-the-art deep cross-modal hashing methods on three widely used benchmark databases, and the experimental results verify its efficiency and superiority. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Image Processing is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Since cross-modal hashing requires minimal storage and computation, it is becoming increasingly popular with the exponential growth of multimedia content on the internet. However, the lack of accurate supervisory data has curtailed the effectiveness of unsupervised hashing techniques. Conversely, supervised hashing strategies necessitate considerable human and financial resources for data annotation. To address this limitation, we propose a novel semi-supervised cross-modal hashing method called Enhanced Cross-Modal Hashing via Hybrid Distillation and Structural Refinement (HDSR). Specifically, we first learn the features of inter-modal and inter-instance similarity relationships through pointwise semantic alignment and listwise similarity partial order learning, respectively, to extract refined structural representations from partially labeled data. Secondly, by fusing inter-modal similarity to construct higher-order affinity matrices, we precisely delineate the semantic correlation information across cross-modal data, facilitating stable self-supervised training of unlabeled data through the application of momentum fusion strategies. Finally, the refined structural representation of labeled data is transferred into unlabeled branches through hybrid distillation, enhancing the performance of cross-modal hash learning by generating compact and accurate hash codes. The proposed HDSR is compared with several state-of-the-art deep cross-modal hashing methods on three widely used benchmark databases, and the experimental results verify its efficiency and superiority. [ABSTRACT FROM AUTHOR]
ISSN:10577149
DOI:10.1109/TIP.2025.3613942